Daily Papers of 2024-12-20

  1. Qwen2.5 Technical Report 328 upvotes, #1 of 2024-12-20
  2. Progressive Multimodal Reasoning via Active Retrieval 67 upvotes, #2 of 2024-12-20
  3. MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval 51 upvotes, #3 of 2024-12-20
  4. How to Synthesize Text Data without Model Collapse? 46 upvotes, #4 of 2024-12-20
  5. LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks 31 upvotes, #5 of 2024-12-20
  6. Flowing from Words to Pixels: A Framework for Cross-Modality Evolution 25 upvotes, #6 of 2024-12-20
  7. Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion 15 upvotes, #7 of 2024-12-20
  8. LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis 14 upvotes, #8 of 2024-12-20
  9. AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling 12 upvotes, #9 of 2024-12-20
  10. DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation 9 upvotes, #10 of 2024-12-20
  11. Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception 6 upvotes, #11 of 2024-12-20
  12. AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation 5 upvotes, #12 of 2024-12-20
  13. UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency 5 upvotes, #12 of 2024-12-20
  14. TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation 4 upvotes, #14 of 2024-12-20
  15. PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation 3 upvotes, #15 of 2024-12-20
  16. Move-in-2D: 2D-Conditioned Human Motion Generation 2 upvotes, #16 of 2024-12-20
  17. DateLogicQA: Benchmarking Temporal Biases in Large Language Models 2 upvotes, #16 of 2024-12-20

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.